ClawHub
Back to skill

Security audit

search for literature on environmental psychology

Security checks across malware telemetry and agentic risk

Overview

This skill is a local PPT-generation helper with an overstated PDF-to-PPT description, but its actual files show no hidden data access, persistence, network use, or destructive behavior.

Install only if you are comfortable preparing the structured paper-analysis JSON yourself. Do not expect these scripts to parse PDFs automatically; they format provided analysis data into a PowerPoint file.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The skill claims an end-to-end PDF-to-PPT automation pipeline, but the documented behavior actually relies on externally prepared analysis JSON and does not implement PDF parsing or content extraction. This mismatch can mislead users into granting trust, supplying sensitive documents, or relying on the skill for processing it does not perform, which creates integrity and data-handling risks in agent environments.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.